claude-secure-coding-rules CLAUDE.md

Repository instructions for a collection of secure coding rules for web applications, AI systems, and agent tools. They describe the rule categories, supported programming languages and frameworks, and repository layout.

In plain words
What is it for?
Use them when adding, reviewing, or organizing security rules for languages, web frameworks, AI libraries, machine-learning systems, or agent tool use.
Why use it?
They give a coding agent the security guidance and file locations needed to apply the project’s rules consistently. This helps avoid overlooking relevant web, AI, or agent security concerns.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/tikitribe/claude-secure-coding-rules/claude-md
Clone the repo
git clone --depth 1 https://github.com/TikiTribe/claude-secure-coding-rules
Per session 2,599 This file is loaded in full into every session.
When invoked 2,599 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.02599 $0.02599
Opus 5 $0.01300 $0.01300
Sonnet 5 $0.00520 $0.00520
Haiku 4.5 $0.00260 $0.00260

Measured 3d ago against content hash 4e88185726e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-secure-coding-rules CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - Secure Coding Rules for Claude Code

This repository provides comprehensive security rules for Claude Code, covering web applications, AI/ML systems, and agentic AI.

Project Overview

Purpose: Open-source security rules that guide Claude Code to generate secure code by default

Coverage:

  • OWASP Top 10 2025 (web application security)
  • OWASP MCP Top 10 2025 (Model Context Protocol security)
  • AI/ML security (NIST AI RMF, MITRE ATLAS, Google SAIF)
  • Agentic AI security (tool use, autonomy, sandboxing)
  • Language-specific rules (Python, JavaScript, TypeScript, Go, Rust, Java, C#, Ruby, R, C++, Julia, SQL)
  • Backend frameworks (FastAPI, Express, Django, Flask, NestJS)
  • AI/ML frameworks (LangChain, CrewAI, AutoGen, Transformers, vLLM, Triton, TorchServe, Ray Serve, BentoML, MLflow, Modal)
  • Frontend frameworks (React, Next.js, Vue, Angular, Svelte)

Repository Structure

claude-secure-coding-rules/
├── rules/
│   ├── _core/                      # Foundation rules (apply to all projects)
│   │   ├── owasp-2025.md          # OWASP Top 10 2025 security rules
│   │   ├── mcp-security.md        # Model Context Protocol (MCP) security rules
│   │   ├── ai-security.md         # AI/ML system security rules
│   │   └── agent-security.md      # Agentic AI security rules
│   │
│   ├── languages/                  # Language-specific security rules
│   │   ├── python/CLAUDE.md       # Deserialization, subprocess, path traversal, crypto, SQL
│   │   ├── javascript/CLAUDE.md   # eval, prototype pollution, DOM security, Node.js
│   │   ├── typescript/CLAUDE.md   # Type safety, validation, any types
│   │   ├── go/CLAUDE.md           # Concurrency, context, templates, error handling
│   │   ├── rust/CLAUDE.md         # unsafe blocks, FFI, memory safety, crypto
│   │   ├── java/CLAUDE.md         # Serialization, JNDI, reflection, streams
│   │   ├── csharp/CLAUDE.md       # .NET patterns, LINQ injection, assemblies
│   │   ├── ruby/CLAUDE.md         # Metaprogramming, ERB, mass assignment
│   │   ├── r/CLAUDE.md            # Shiny apps, data security, package verification
│   │   ├── cpp/CLAUDE.md          # Memory safety, buffer overflows, smart pointers
│   │   ├── julia/CLAUDE.md        # Metaprogramming, type safety, serialization
│   │   └── sql/CLAUDE.md          # Injection, permissions, stored procedures
│   │
│   ├── backend/                    # Backend framework rules
│   │   ├── fastapi/CLAUDE.md      # Pydantic validation, JWT, authorization, CORS, AI APIs
│   │   ├── express/CLAUDE.md      # Helmet, sessions, rate limiting, file uploads
│   │   ├── django/CLAUDE.md       # ORM, CSRF, templates, settings
│   │   ├── flask/CLAUDE.md        # Werkzeug, sessions, blueprints, extensions
│   │   ├── nestjs/CLAUDE.md       # Decorators, guards, pipes, interceptors
│   │   ├── langchain/CLAUDE.md    # Prompt injection, tool security, chains, RAG
│   │   ├── crewai/CLAUDE.md       # Multi-agent trust, delegation, memory isolation
│   │   ├── autogen/CLAUDE.md      # Code execution, human-in-loop, sandboxing
│   │   ├── transformers/CLAUDE.md # Model loading, tokenizers, fine-tuning
│   │   ├── vllm/CLAUDE.md         # KV cache, PagedAttention, batching security
│   │   ├── triton/CLAUDE.md       # GPU isolation, ensemble security, gRPC
│   │   ├── torchserve/CLAUDE.md   # MAR files, custom handlers, management API
│   │   ├── ray-serve/CLAUDE.md    # Deployment, autoscaling, serialization
│   │   ├── bentoml/CLAUDE.md      # Bento packaging, runners, API security
│   │   ├── mlflow/CLAUDE.md       # Model registry, experiment tracking, artifacts
│   │   └── modal/CLAUDE.md        # Serverless functions, secrets, containers
│   │
│   └── frontend/                   # Frontend framework rules
│       ├── react/CLAUDE.md        # XSS prevention, state management, CSRF, forms
│       ├── nextjs/CLAUDE.md       # Server Components, Server Actions, middleware, env vars
│       ├── vue/CLAUDE.md          # v-html, computed properties, Vuex, router guards
│       ├── angular/CLAUDE.md      # DomSanitizer, template injection, HTTP client
│       └── svelte/CLAUDE.md       # {@html}, stores, SSR, form actions
│
│   ├── containers/                 # Container security rules
│   │   ├── _core/container-security.md  # Core container principles
│   │   ├── docker/CLAUDE.md       # Docker (images, runtime, scanning, dependencies)
│   │   ├── kubernetes/CLAUDE.md   # Kubernetes (PSS, RBAC, NetworkPolicies, supply chain)
│   │   └── helm/CLAUDE.md         # Helm (secrets, security context, schema, provenance)
│   │
│   ├── iac/                        # Infrastructure as Code rules
│   │   ├── _core/iac-security.md  # Core IaC security principles
│   │   ├── terraform/CLAUDE.md    # Terraform (state, modules, providers)
│   │   └── pulumi/CLAUDE.md       # Pulumi (secrets, CrossGuard, ESC)
│   │
│   └── cicd/                       # CI/CD security rules
│       ├── _core/cicd-security.md  # Core CI/CD principles
│       ├── github-actions/CLAUDE.md  # GitHub Actions (SHA pinning, OIDC)
│       └── gitlab-ci/CLAUDE.md      # GitLab CI (protected vars, scanning)
│
├── templates/                      # Templates for adding new rules
│   ├── rule-template.md           # Template for individual rules
│   └── framework-template.md      # Template for framework rule sets
│
├── docs/                           # Documentation and guides
│   └── CONTRIBUTING.md            # Contribution guidelines with quality standards
│
├── compliance/                     # Compliance mapping (future)
│
├── CLAUDE.md                       # This file - project instructions
├── README.md                       # User documentation and implementation guide
└── LICENSE                         # MIT License

Read the full file on GitHub · 215 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 215 lines · 2,599 tokens per session scan A 4e88185726e5

Subscribe to this mod's changes

claude-secure-coding-rules CLAUDE.md is an instructions file published in the GitHub repository TikiTribe/claude-secure-coding-rules (140 stars, last pushed 3mo ago), licensed MIT. It adds 2,599 tokens to every session, about $0.0130 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.